BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:BAMBI: Combining Neural Networks and Nested Sampling for Rapid Bay
 esian Analysis - Philip Graff (Cavendish Astrophysics)
DTSTART:20111122T170000Z
DTEND:20111122T173000Z
UID:TALK33449@talks.cam.ac.uk
CONTACT:David Titterington
DESCRIPTION:I will present an algorithm for rapid Bayesian analysis that c
 ombines the benefits of nested sampling and artificial neural networks. Th
 e blind accelerated multimodal Bayesian inference (BAMBI) algorithm implem
 ents the MultiNest package for nested sampling as well as the training of 
 an artificial neural network (NN) to learn the likelihood function. In the
  case of computationally expensive likelihoods\, this allows the substitut
 ion of a much more rapid approximation in order to increase significantly 
 the speed of the analysis. I first demonstrate\, with a few toy examples\,
  the ability of a NN to learn complicated likelihood surfaces. BAMBI's abi
 lity to decrease running time for Bayesian inference is then demonstrated 
 in the context of estimating cosmological parameters from WMAP and other o
 bservations. Valuable speed increases are achieved in addition to obtainin
 g NNs trained on the likelihood functions for the different model and data
  combinations. These NNs can then be used for an even faster follow-up ana
 lysis using the same likelihood and different priors. This is a fully gene
 ral algorithm that can be applied\, without any pre-processing\, to other 
 problems with computationally expensive likelihood functions.\n
LOCATION:Ryle Seminar Room\, Cavendish Laboratory
END:VEVENT
END:VCALENDAR